Let's build a RAG App with Llama2 (Cloudflare Workers AI, Vectorize)

preview_player
Показать описание
In this workshop, Kristian Freeman, Cloudflare Developer Advocate, shows how to build an Retrieval Augmented Generation app using Workers AI and Vectorize.

----------------------------------------

Deploy serverless code instantly across the globe to give it exceptional performance, reliability, and scale, with Cloudflare Workers.

#CloudflareWorkers #DeveloperQuickTakes #Streaming #CloudflareStream #CloudflareTutorials #Developer
Рекомендации по теме
Комментарии
Автор

Gracias, este tipo de material me ayuda un monton!

-not-found-service
Автор

i loved this video. also you look like Daniel Radcliff. EXPECTO VECTORIZE !!

gagansuie
Автор

In this case, D1 becomes part of LLM, right?

xiaoyulv
Автор

Why do we need vector? Is it like faster database retrieval?

bishwasmishra
Автор

seemslike we can not create vectorize with free plans (=

danial_hamedi
Автор

sigh ... was expecting a more polished presentation

SoloJetMan